paper-with-me

홈 › Papers

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

2020-05-14 · ICML 2020 1 · Kimin Lee, Younggyo Seo, Seung-Hyun Lee, Honglak Lee, Jinwoo Shin

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a challenging task. To tackle this problem, we decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it. In order to encode dynamics-specific information into the context latent vector, we introduce a novel loss function that encourages the context latent vector to be useful for predicting both forward and backward dynamics. The proposed method achieves superior generalization ability across various simulated robotics and control tasks, compared to existing RL schemes.

📄 PDF Abstract BibTeX arXiv:2005.06800

Code (2)

younggyoseo/CaDM 공식 구현 tf
ZhengXinyue/fuck_papers

Tasks

modelModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning

2022-11-23 · Junjie Wang, Yao Mu, Dong Li, Qichao Zhang 외

The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remai…

Model-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization

2025-08-27 · Frank Röder, Jan Benad, Manfred Eppe, Pradeep Kr. Banerjee arxiv

Real-world reinforcement learning demands adaptation to unseen environmental conditions without costly retraining. Contextual Markov Decision Processes (cMDP) model this challenge, but existing methods often require expl…

Zero-shot GeneralizationReinforcement Learning

Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem

2025-09-19 · Chao Li, Bingkun Bao, Yang Gao arxiv

This paper studies fully decentralized cooperative multi-agent reinforcement learning, where each agent solely observes the states, its local actions, and the shared rewards. The inability to access other agents' actions…

Multi-agent Reinforcement Learning

Context-Aware Model-Based Reinforcement Learning for Autonomous Racing

2025-10-13 · Emran Yasser Moustafa, Ivana Dusparic arxiv

Autonomous vehicles have shown promising potential to be a groundbreaking technology for improving the safety of road users. For these vehicles, as well as many other safety-critical robotic technologies, to be deployed …

Reinforcement LearningAutonomous VehiclesAutonomous Driving

Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

2022-10-09 · Yao Mu, Yuzheng Zhuang, Fei Ni, Bin Wang 외

Adapting to the changes in transition dynamics is essential in robotic applications. By learning a conditional policy with a compact context, context-aware meta-reinforcement learning provides a flexible way to adjust be…

Decision MakingMeta Reinforcement Learningreinforcement-learningReinforcement Learning+1